This document was prepared on 2021-11-11.
library(tidyverse)
library(patchwork)
library(glmmTMB)
library(report)
library(parameters)
library(correlation)
library(modelbased)
library(performance)
library(see)
summary(report::report(sessionInfo()))The analysis was done using the R Statistical language (v4.1.1; R Core Team, 2021) on Windows 10 x64, using the packages effectsize (v0.4.5.4), ggplot2 (v3.3.5), stringr (v1.4.0), forcats (v0.5.1), tidyr (v1.1.4), readr (v2.0.2), dplyr (v1.0.7), tibble (v3.1.4), purrr (v0.3.4), parameters (v0.15.0.1), insight (v0.14.5.1), performance (v0.7.3.5), see (v0.7.0.1), easystats (v0.4.3), correlation (v0.7.1.1), modelbased (v0.7.0.1), bayestestR (v0.11.5), report (v0.4.0), datawizard (v0.2.1.9000), glmmTMB (v1.1.2.3), patchwork (v1.1.1) and tidyverse (v1.3.1).
# setwd("C:/Users/user/Desktop/Sputnik/2019-23/DeceptionInteroTom")
df <- read.csv("data/data_combined.csv") %>%
mutate(ID = as.factor(paste0("S", ID)),
condition = as.factor(condition),
item = as.factor(item),
style = as.factor(style),
instruction = as.factor(instruction)) |>
#TODO: This renaming should be done at the preprocessing stage
rename("Participant" = "ID",
"Condition" = "condition",
"Item" = "item",
"Phrasing" = "style",
"Answer" = "instruction",
"YONI_Total" = "yoni_total",
"YONI_Affective" = "yoni_affective",
"YONI_Cognitive" = "yoni_cognitive",
"YONI_Physical" = "yoni_physical",
"BES_Total" = "BES_total",
"BES_Cognitive" = "BES_cognitive",
"BES_Affective" = "BES_affective",
"HCT_Confidence" = "HCT_confidence",
"HCT_Accuracy" = "HCT_accuracy",
"HCT_Awareness" = "HCT_awareness",
"MAIA_Total" = "MAIA_total",
"MAIA_AttentionRegulation" = "MAIA_attention_regulation",
"MAIA_BodyListening" = "MAIA_body_listening",
"MAIA_EmotionalAwareness" = "MAIA_emotional_awareness",
"MAIA_NotDistracting" = "MAIA_not_distracting",
"MAIA_NotWorrying" = "MAIA_not_worrying",
"MAIA_Noticing" = "MAIA_noticing",
"MAIA_SelfRegulation" = "MAIA_self_regulation",
"MAIA_Trusting" = "MAIA_trusting",
"LIE_Ability" = "lie_ability",
"LIE_Frequency" = "lie_frequency",
"LIE_Negativity" = "lie_negativity",
"LIE_Contextuality" = "lie_contextuality",
"Confidence" = "DT_confidence",
"RT" = "DT_RT") |>
mutate(Answer = fct_recode(Answer, Lie = "LIE", Truth = "TRUTH")) |>
select(-HCT_guess, -HCT_noguess, -HCT_onebreath)
cat(paste("The data consists of",
report::report_participants(df,
participants = "Participant",
sex = "Gender",
age = "Age")))The data consists of 30 participants (Mean age = 21.1, SD = 2.1, range: [18, 25]; 63.3% females)
df %>%
group_by(Participant) %>%
select(starts_with("YONI_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_manual(values = c("YONI (Affective)" = "Purple",
"YONI (Cognitive)" = "Blue",
"YONI (Physical)" = "Green",
"YONI (Total)"= "DarkBlue"),
guide = "none") +
facet_wrap(~name, scales = "free")df %>%
group_by(Participant) %>%
select(starts_with("BES_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_manual(values = c("BES (Affective)" = "Purple",
"BES (Cognitive)" = "Blue",
"BES (Total)"= "DarkBlue"),
guide = "none") +
facet_wrap(~name, scales = "free")df %>%
group_by(Participant) %>%
select(starts_with("HCT_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_manual(values = c("HCT (Accuracy)" = "Red",
"HCT (Awareness)" = "Orange",
"HCT (Confidence)"= "DarkOrange"),
guide = "none") +
facet_wrap(~name, scales = "free")> Warning: Removed 6 rows containing non-finite values (stat_density).
df %>%
group_by(Participant) %>%
select(starts_with("MAIA_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_brewer(palette = "Reds", guide = "none") +
facet_wrap(~name, scales = "free")df %>%
group_by(Participant) %>%
select(starts_with("LIE_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_manual(values = c("LIE (Ability)" = "#2196F3",
"LIE (Frequency)" = "#4CAF50",
"LIE (Contextuality)"= "#FF9800",
"LIE (Negativity)"= "#E91E63"),
guide = "none") +
facet_wrap(~name, scales = "free")df |>
group_by(Participant, Answer) |>
summarise(Confidence = paste(insight::format_value(mean(Confidence, na.rm = TRUE)),
" +- ",
insight::format_value(sd(Confidence, na.rm = TRUE))),
RT = paste(insight::format_value(mean(RT, na.rm = TRUE)),
" +- ",
insight::format_value(sd(RT, na.rm = TRUE)))) |>
arrange(Participant) |>
knitr::kable()| Participant | Answer | Confidence | RT |
|---|---|---|---|
| S1 | Lie | 0.40 +- 0.10 | 3.69 +- 0.69 |
| S1 | Truth | 0.52 +- 0.15 | 3.75 +- 0.79 |
| S10 | Lie | 0.59 +- 0.28 | 3.20 +- 0.71 |
| S10 | Truth | 0.84 +- 0.13 | 3.22 +- 0.62 |
| S11 | Lie | 0.38 +- 0.31 | 3.60 +- 0.69 |
| S11 | Truth | 0.72 +- 0.26 | 3.48 +- 0.62 |
| S12 | Lie | 0.58 +- 0.13 | 3.77 +- 1.42 |
| S12 | Truth | 0.64 +- 0.16 | 4.40 +- 1.72 |
| S13 | Lie | 0.28 +- 0.25 | 7.22 +- 0.82 |
| S13 | Truth | 0.85 +- 0.17 | 7.57 +- 0.81 |
| S14 | Lie | 0.52 +- 0.29 | 4.13 +- 0.86 |
| S14 | Truth | 0.62 +- 0.26 | 5.29 +- 1.54 |
| S15 | Lie | +- | 4.38 +- 0.94 |
| S15 | Truth | +- | 4.15 +- 1.04 |
| S16 | Lie | 0.41 +- 0.18 | 4.94 +- 1.13 |
| S16 | Truth | 0.66 +- 0.11 | 5.07 +- 1.01 |
| S17 | Lie | 0.63 +- 0.31 | 2.72 +- 0.63 |
| S17 | Truth | 0.77 +- 0.19 | 2.72 +- 0.51 |
| S18 | Lie | 0.21 +- 0.33 | 5.88 +- 2.54 |
| S18 | Truth | 0.79 +- 0.36 | 5.13 +- 1.98 |
| S19 | Lie | +- | 3.44 +- 1.55 |
| S19 | Truth | +- | 3.71 +- 2.05 |
| S2 | Lie | 0.10 +- 0.17 | 6.46 +- 1.95 |
| S2 | Truth | 0.94 +- 0.08 | 6.83 +- 1.71 |
| S20 | Lie | 0.37 +- 0.32 | 3.79 +- 0.74 |
| S20 | Truth | 0.80 +- 0.17 | 4.04 +- 1.02 |
| S21 | Lie | 0.55 +- 0.12 | 4.97 +- 1.01 |
| S21 | Truth | 0.74 +- 0.18 | 5.09 +- 1.04 |
| S22 | Lie | 0.13 +- 0.29 | 4.78 +- 2.94 |
| S22 | Truth | 0.81 +- 0.36 | 5.12 +- 2.99 |
| S23 | Lie | +- | 3.10 +- 1.18 |
| S23 | Truth | +- | 2.99 +- 0.80 |
| S24 | Lie | 0.27 +- 0.22 | 2.81 +- 0.68 |
| S24 | Truth | 0.72 +- 0.17 | 2.69 +- 0.64 |
| S25 | Lie | 0.63 +- 0.33 | 3.71 +- 1.11 |
| S25 | Truth | 0.85 +- 0.22 | 3.71 +- 0.92 |
| S26 | Lie | 0.46 +- 0.21 | 3.32 +- 0.61 |
| S26 | Truth | 0.70 +- 0.16 | 3.23 +- 0.53 |
| S27 | Lie | 0.32 +- 0.09 | 5.19 +- 1.88 |
| S27 | Truth | 0.68 +- 0.07 | 4.75 +- 1.78 |
| S28 | Lie | 0.49 +- 0.36 | 3.78 +- 0.83 |
| S28 | Truth | 0.59 +- 0.32 | 3.69 +- 0.50 |
| S29 | Lie | 0.58 +- 0.50 | 3.22 +- 0.56 |
| S29 | Truth | 0.90 +- 0.30 | 3.31 +- 0.68 |
| S3 | Lie | +- | 3.35 +- 0.80 |
| S3 | Truth | +- | 3.42 +- 0.96 |
| S30 | Lie | 0.80 +- 0.28 | 4.09 +- 1.10 |
| S30 | Truth | 0.88 +- 0.18 | 3.80 +- 0.99 |
| S4 | Lie | 0.67 +- 0.18 | 3.86 +- 0.89 |
| S4 | Truth | 0.77 +- 0.13 | 3.81 +- 0.80 |
| S5 | Lie | 0.53 +- 0.23 | 3.41 +- 0.63 |
| S5 | Truth | 0.72 +- 0.21 | 3.45 +- 0.69 |
| S6 | Lie | 0.11 +- 0.15 | 3.10 +- 0.52 |
| S6 | Truth | 0.90 +- 0.09 | 3.24 +- 0.64 |
| S7 | Lie | 0.62 +- 0.33 | 3.84 +- 0.58 |
| S7 | Truth | 0.69 +- 0.29 | 3.69 +- 0.55 |
| S8 | Lie | 0.44 +- 0.17 | 4.48 +- 0.95 |
| S8 | Truth | 0.71 +- 0.16 | 4.59 +- 1.12 |
| S9 | Lie | 5.79e-04 +- 9.06e-04 | 4.75 +- 1.42 |
| S9 | Truth | 1.00 +- 1.18e-03 | 5.15 +- 1.88 |
df <- df |>
dplyr::filter(Participant != "S9", # Extreme answers
!Participant %in% c("S3", "S15", "S19", "S23")) # No datap1 <- df |>
dplyr::filter(!Participant %in% c("S29")) |>
ggplot(aes(x = Confidence, fill = Participant)) +
geom_density(alpha = 0.1) +
see::scale_fill_material_d(palette = "rainbow", guide = "none") +
see::theme_modern() +
scale_x_continuous(labels = scales::percent, expand=expansion(c(0, .05))) +
scale_y_continuous(expand=expansion(c(0, .05))) +
facet_wrap(~Answer)
p2 <- df |>
dplyr::filter(!Participant %in% c("S29")) |>
ggplot(aes(x = RT, fill = Participant)) +
geom_density(alpha = 0.1) +
see::scale_fill_material_d(palette = "rainbow", guide = "none") +
scale_x_continuous(expand=expansion(c(0, .05))) +
scale_y_continuous(expand=expansion(c(0, .05))) +
facet_wrap(~Answer)
p1 / p2dfsub <- df |>
select(Participant,
starts_with("YONI_"),
starts_with("BES_"),
starts_with("HCT_"),
starts_with("MAIA_"),
starts_with("LIE_")) |>
group_by(Participant) |>
summarise_all(mean)r <- correlation(select(dfsub, starts_with("YONI_")),
select(dfsub, starts_with("BES_")),
p_adjust = "none")
summary(r) |>
plot()r <- correlation(select(dfsub, starts_with("MAIA_")),
select(dfsub, starts_with("HCT_")),
p_adjust = "none")
summary(r) |>
plot()r <- correlation(select(dfsub, starts_with(c("MAIA_", "HCT_"))),
select(dfsub, starts_with(c("YONI_", "BES_"))),
p_adjust = "none")
summary(r) |>
plot()model <- glmmTMB(RT ~ Answer * Phrasing + (1|Participant) + (1|Item), data = df)
parameters::parameters(model, effects = "fixed")> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------
> (Intercept) | 4.01 | 0.24 | [ 3.54, 4.47] | 16.80 | < .001
> Answer [Truth] | 0.03 | 0.07 | [-0.11, 0.17] | 0.39 | 0.694
> Phrasing [Indirect] | 0.33 | 0.07 | [ 0.19, 0.48] | 4.58 | < .001
> Answer [Truth] * Phrasing [Indirect] | 0.08 | 0.10 | [-0.12, 0.28] | 0.79 | 0.429
estimate_means(model, at = c("Answer", "Phrasing")) |>
plot(show_data = "none") model <- glmmTMB(Confidence ~ Answer * Phrasing + (1|Participant) + (1|Item), data = df)
parameters::parameters(model)> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------
> (Intercept) | 0.45 | 0.02 | [ 0.41, 0.49] | 20.53 | < .001
> Answer [Truth] | 0.31 | 0.02 | [ 0.28, 0.34] | 18.53 | < .001
> Phrasing [Indirect] | -0.02 | 0.02 | [-0.05, 0.02] | -0.93 | 0.353
> Answer [Truth] * Phrasing [Indirect] | 2.98e-03 | 0.02 | [-0.04, 0.05] | 0.13 | 0.899
>
> # Random Effects
>
> Parameter | Coefficient | 95% CI
> --------------------------------------------------------
> SD (Intercept: Participant) | 0.09 | [0.07, 0.13]
> SD (Intercept: Item) | 7.89e-03 | [0.07, 0.13]
> SD (Residual) | 0.26 | [0.25, 0.27]
estimate_means(model, at = c("Answer", "Phrasing")) |>
plot(show_data = "none") # Adjustments for beta models
df$Confidence[df$Confidence == 1] <- 0.99999
df$Confidence[df$Confidence == 0] <- 0.00001
model <- glmmTMB(Confidence ~ RT * Answer + Phrasing + (1|Participant) + (1|Item),
data = df, family = beta_family())
parameters::parameters(model, effects = "fixed")> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> --------------------------------------------------------------------------
> (Intercept) | 0.77 | 0.13 | [ 0.51, 1.04] | 5.80 | < .001
> RT | -0.25 | 0.03 | [-0.30, -0.20] | -9.53 | < .001
> Answer [Truth] | -0.02 | 0.15 | [-0.31, 0.26] | -0.16 | 0.876
> Phrasing [Indirect] | -1.08e-03 | 0.05 | [-0.11, 0.10] | -0.02 | 0.984
> RT * Answer [Truth] | 0.29 | 0.03 | [ 0.23, 0.35] | 9.03 | < .001
estimate_relation(model, at = c("RT", "Answer")) |>
plot(length = 50, point = list(alpha = 0.3, size = 3.5)) model <- glmmTMB(Confidence ~ Answer * Condition + (1|Participant) + (1|Item),
data = df, family = beta_family())
parameters::parameters(model, effects = "fixed")> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------
> (Intercept) | -0.34 | 0.08 | [-0.51, -0.18] | -4.08 | < .001
> Answer [Truth] | 1.29 | 0.08 | [ 1.14, 1.44] | 16.45 | < .001
> Condition [Social] | 0.14 | 0.08 | [-0.01, 0.29] | 1.78 | 0.075
> Answer [Truth] * Condition [Social] | -0.22 | 0.11 | [-0.43, -0.01] | -2.06 | 0.039
estimate_means(model, at = c("Condition", "Answer")) |>
plot(show_data = "none") model <- glmmTMB(RT ~ Answer * Condition + (1|Participant) + (1|Item),
data = df)
parameters::parameters(model, effects = "fixed")> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------
> (Intercept) | 4.42 | 0.24 | [ 3.96, 4.89] | 18.57 | < .001
> Answer [Truth] | 0.07 | 0.07 | [-0.07, 0.21] | 1.00 | 0.316
> Condition [Social] | -0.51 | 0.07 | [-0.65, -0.37] | -7.05 | < .001
> Answer [Truth] * Condition [Social] | -5.48e-03 | 0.10 | [-0.20, 0.19] | -0.05 | 0.957
estimate_means(model, at = c("Condition", "Answer")) |>
plot(show_data = "none") model <- glmmTMB(Confidence ~ Answer / (Condition * YONI_Total) + (1|Participant) + (1|Item),
data = df, family = beta_family())
get_parameters <- function(model) {
# Parameters
params <- parameters::parameters(model, effects = "fixed")
# Marginal effects
at <- c("Answer", "Condition")
trend <- insight::find_predictors(model)$conditional
trend <- trend[!trend %in% at]
marg <- modelbased::estimate_slopes(model, trend = trend, at = at)
# Output
list(params = params, marginal_effects = marg)
}
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ----------------------------------------------------------------------------------------------------
> (Intercept) | 2.70 | 0.95 | [ 0.84, 4.56] | 2.85 | 0.004
> Answer [Truth] | -3.67 | 0.89 | [-5.41, -1.92] | -4.12 | < .001
> Answer [Lie] * ConditionSocial | -2.47 | 0.90 | [-4.23, -0.71] | -2.76 | 0.006
> Answer [Truth] * ConditionSocial | 2.06 | 0.88 | [ 0.35, 3.78] | 2.36 | 0.018
> Answer [Lie] * YONI Total | -0.04 | 0.01 | [-0.06, -0.01] | -3.22 | 0.001
> Answer [Truth] * YONI Total | 0.02 | 0.01 | [ 0.00, 0.04] | 2.04 | 0.041
> Answer [Lie] * ConditionSocial * YONI Total | 0.03 | 0.01 | [ 0.01, 0.05] | 2.91 | 0.004
> Answer [Truth] * ConditionSocial * YONI Total | -0.03 | 0.01 | [-0.05, -0.01] | -2.46 | 0.014
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | -0.04 | 0.01 | [-0.06, -0.01] | -3.22 | 0.001
> Social | Lie | -5.13e-03 | 0.01 | [-0.03, 0.02] | -0.46 | 0.643
> Polygraph | Truth | 0.02 | 0.01 | [ 0.00, 0.04] | 2.04 | 0.042
> Social | Truth | -2.66e-03 | 0.01 | [-0.02, 0.02] | -0.24 | 0.807
> Marginal effects estimated for YONI_Total
plot_effect <- function(model, var = "YONI_Total", outcome = "Confidence") {
data <- df |>
group_by(Participant, Answer, Condition) |>
summarise({{var}} := mean(.data[[var]], na.rm = TRUE),
SD = sd(.data[[outcome]], na.rm = TRUE),
{{outcome}} := mean(.data[[outcome]], na.rm = TRUE),
CI_low = .data[[outcome]] - SD / 2,
CI_high = .data[[outcome]] + SD / 2)
dodge_width <- 0.02 * diff(range(data[[var]]))
ylab <- ifelse(outcome == "RT", "Reaction Time (s)", "Confidence")
link_data <- estimate_relation(model, at = c("Condition", var, "Answer"), length = 30)
ggplot(link_data, aes_string(x = var, y = "Predicted")) +
geom_pointrange(data = data, aes_string(y = outcome, color = "Condition", ymin = "CI_low", ymax = "CI_high"), position = position_dodge(width = dodge_width)) +
geom_ribbon(aes(ymin = CI_low, ymax = CI_high, fill = Condition), alpha = 0.33) +
geom_line(aes(color = Condition)) +
labs(y = ylab, x = paste0(stringr::str_replace(var, "_", " ("), ")")) +
scale_color_manual(values = c("Polygraph" = "#FF5722", "Social" = "#2196F3")) +
scale_fill_manual(values = c("Polygraph" = "#FF5722", "Social" = "#2196F3")) +
facet_wrap(~Answer)
}
p_conf_yoni_total <- plot_effect(model, var = "YONI_Total", outcome = "Confidence")
# p_conf_yoni_totalmodel <- glmmTMB(RT ~ Answer / (Condition * YONI_Total) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> --------------------------------------------------------------------------------------------------------
> (Intercept) | 0.60 | 2.53 | [-4.37, 5.57] | 0.24 | 0.813
> Answer [Truth] | 2.81 | 0.81 | [ 1.23, 4.40] | 3.48 | < .001
> Answer [Lie] * ConditionSocial | 1.35 | 0.81 | [-0.24, 2.93] | 1.67 | 0.095
> Answer [Truth] * ConditionSocial | -1.49 | 0.81 | [-3.07, 0.09] | -1.85 | 0.065
> Answer [Lie] * YONI Total | 0.04 | 0.03 | [-0.01, 0.10] | 1.52 | 0.130
> Answer [Truth] * YONI Total | 0.01 | 0.03 | [-0.05, 0.07] | 0.43 | 0.668
> Answer [Lie] * ConditionSocial * YONI Total | -0.02 | 9.42e-03 | [-0.04, 0.00] | -2.30 | 0.021
> Answer [Truth] * ConditionSocial * YONI Total | 0.01 | 9.42e-03 | [-0.01, 0.03] | 1.22 | 0.223
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | 0.04 | 0.03 | [-0.01, 0.10] | 1.52 | 0.130
> Social | Lie | 0.02 | 0.03 | [-0.03, 0.08] | 0.78 | 0.435
> Polygraph | Truth | 0.01 | 0.03 | [-0.05, 0.07] | 0.43 | 0.668
> Social | Truth | 0.02 | 0.03 | [-0.03, 0.08] | 0.82 | 0.414
> Marginal effects estimated for YONI_Total
p_rt_yoni_total <- plot_effect(model, var = "YONI_Total", outcome = "RT")
# p_rt_yoni_totalmodel <- glmmTMB(Confidence ~ Answer / (Condition * YONI_Cognitive) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> --------------------------------------------------------------------------------------------------------
> (Intercept) | 3.32 | 0.82 | [ 1.71, 4.94] | 4.03 | < .001
> Answer [Truth] | -3.68 | 0.77 | [-5.19, -2.18] | -4.80 | < .001
> Answer [Lie] * ConditionSocial | -3.13 | 0.78 | [-4.66, -1.60] | -4.00 | < .001
> Answer [Truth] * ConditionSocial | 1.24 | 0.76 | [-0.24, 2.73] | 1.64 | 0.101
> Answer [Lie] * YONI Cognitive | -0.12 | 0.03 | [-0.17, -0.07] | -4.47 | < .001
> Answer [Truth] * YONI Cognitive | 0.04 | 0.03 | [-0.01, 0.09] | 1.60 | 0.109
> Answer [Lie] * ConditionSocial * YONI Cognitive | 0.10 | 0.03 | [ 0.06, 0.15] | 4.19 | < .001
> Answer [Truth] * ConditionSocial * YONI Cognitive | -0.04 | 0.02 | [-0.09, 0.00] | -1.75 | 0.079
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> ---------------------------------------------------------------------------
> Polygraph | Lie | -0.12 | 0.03 | [-0.17, -0.07] | -4.47 | < .001
> Social | Lie | -0.01 | 0.03 | [-0.07, 0.04] | -0.49 | 0.624
> Polygraph | Truth | 0.04 | 0.03 | [-0.01, 0.09] | 1.60 | 0.109
> Social | Truth | -3.60e-04 | 0.03 | [-0.05, 0.05] | -0.01 | 0.989
> Marginal effects estimated for YONI_Cognitive
p_conf_yoni_cognitive <- plot_effect(model, var = "YONI_Cognitive", outcome = "Confidence")
# p_conf_yoni_cognitivemodel <- glmmTMB(RT ~ Answer / (Condition * YONI_Cognitive) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> --------------------------------------------------------------------------------------------------------
> (Intercept) | 0.42 | 2.24 | [-3.96, 4.80] | 0.19 | 0.851
> Answer [Truth] | 2.39 | 0.72 | [ 0.98, 3.79] | 3.32 | < .001
> Answer [Lie] * ConditionSocial | 1.60 | 0.72 | [ 0.19, 3.01] | 2.22 | 0.026
> Answer [Truth] * ConditionSocial | -1.03 | 0.72 | [-2.44, 0.38] | -1.44 | 0.151
> Answer [Lie] * YONI Cognitive | 0.13 | 0.07 | [-0.01, 0.27] | 1.80 | 0.072
> Answer [Truth] * YONI Cognitive | 0.05 | 0.07 | [-0.09, 0.20] | 0.76 | 0.447
> Answer [Lie] * ConditionSocial * YONI Cognitive | -0.07 | 0.02 | [-0.11, -0.02] | -2.95 | 0.003
> Answer [Truth] * ConditionSocial * YONI Cognitive | 0.02 | 0.02 | [-0.03, 0.06] | 0.73 | 0.468
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | 0.13 | 0.07 | [-0.01, 0.27] | 1.80 | 0.072
> Social | Lie | 0.06 | 0.07 | [-0.08, 0.20] | 0.85 | 0.393
> Polygraph | Truth | 0.05 | 0.07 | [-0.09, 0.20] | 0.76 | 0.447
> Social | Truth | 0.07 | 0.07 | [-0.07, 0.21] | 0.99 | 0.320
> Marginal effects estimated for YONI_Cognitive
p_rt_yoni_cognitive <- plot_effect(model, var = "YONI_Cognitive", outcome = "RT")
# p_rt_yoni_cognitivemodel <- glmmTMB(Confidence ~ Answer / (Condition * YONI_Affective) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------------------
> (Intercept) | 0.30 | 1.07 | [-1.80, 2.41] | 0.28 | 0.777
> Answer [Truth] | -0.09 | 1.02 | [-2.10, 1.91] | -0.09 | 0.927
> Answer [Lie] * ConditionSocial | -1.29 | 1.02 | [-3.29, 0.70] | -1.27 | 0.204
> Answer [Truth] * ConditionSocial | 1.40 | 1.02 | [-0.59, 3.39] | 1.38 | 0.168
> Answer [Lie] * YONI Affective | -0.02 | 0.03 | [-0.06, 0.03] | -0.61 | 0.544
> Answer [Truth] * YONI Affective | 0.02 | 0.03 | [-0.03, 0.07] | 0.68 | 0.498
> Answer [Lie] * ConditionSocial * YONI Affective | 0.03 | 0.02 | [-0.01, 0.08] | 1.41 | 0.159
> Answer [Truth] * ConditionSocial * YONI Affective | -0.04 | 0.02 | [-0.08, 0.01] | -1.47 | 0.142
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | -0.02 | 0.03 | [-0.06, 0.03] | -0.61 | 0.544
> Social | Lie | 0.02 | 0.03 | [-0.03, 0.07] | 0.72 | 0.469
> Polygraph | Truth | 0.02 | 0.03 | [-0.03, 0.07] | 0.68 | 0.498
> Social | Truth | -0.02 | 0.03 | [-0.07, 0.03] | -0.71 | 0.478
> Marginal effects estimated for YONI_Affective
p_conf_yoni_affective <- plot_effect(model, var = "YONI_Affective", outcome = "Confidence")
# p_conf_yoni_affectivemodel <- glmmTMB(RT ~ Answer / (Condition * YONI_Affective) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------------------
> (Intercept) | 1.12 | 2.88 | [-4.53, 6.77] | 0.39 | 0.698
> Answer [Truth] | 2.06 | 0.92 | [ 0.26, 3.86] | 2.24 | 0.025
> Answer [Lie] * ConditionSocial | 0.27 | 0.92 | [-1.53, 2.07] | 0.30 | 0.766
> Answer [Truth] * ConditionSocial | -1.72 | 0.92 | [-3.52, 0.08] | -1.87 | 0.061
> Answer [Lie] * YONI Affective | 0.08 | 0.07 | [-0.05, 0.21] | 1.15 | 0.250
> Answer [Truth] * YONI Affective | 0.03 | 0.07 | [-0.10, 0.16] | 0.46 | 0.647
> Answer [Lie] * ConditionSocial * YONI Affective | -0.02 | 0.02 | [-0.06, 0.02] | -0.85 | 0.394
> Answer [Truth] * ConditionSocial * YONI Affective | 0.03 | 0.02 | [-0.01, 0.07] | 1.32 | 0.187
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | 0.08 | 0.07 | [-0.06, 0.21] | 1.15 | 0.250
> Social | Lie | 0.06 | 0.07 | [-0.07, 0.19] | 0.88 | 0.380
> Polygraph | Truth | 0.03 | 0.07 | [-0.10, 0.16] | 0.46 | 0.647
> Social | Truth | 0.06 | 0.07 | [-0.07, 0.19] | 0.88 | 0.380
> Marginal effects estimated for YONI_Affective
p_rt_yoni_affective <- plot_effect(model, var = "YONI_Affective", outcome = "RT")
# p_rt_yoni_affectivemodel <- glmmTMB(Confidence ~ Answer / (Condition * YONI_Physical) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------------------
> (Intercept) | 0.87 | 0.40 | [ 0.09, 1.65] | 2.18 | 0.029
> Answer [Truth] | -1.06 | 0.37 | [-1.79, -0.34] | -2.87 | 0.004
> Answer [Lie] * ConditionSocial | -0.42 | 0.37 | [-1.15, 0.30] | -1.14 | 0.253
> Answer [Truth] * ConditionSocial | 0.99 | 0.37 | [ 0.28, 1.71] | 2.71 | 0.007
> Answer [Lie] * YONI Physical | -0.10 | 0.03 | [-0.16, -0.04] | -3.11 | 0.002
> Answer [Truth] * YONI Physical | 0.09 | 0.03 | [ 0.03, 0.16] | 2.94 | 0.003
> Answer [Lie] * ConditionSocial * YONI Physical | 0.05 | 0.03 | [-0.01, 0.10] | 1.52 | 0.128
> Answer [Truth] * ConditionSocial * YONI Physical | -0.09 | 0.03 | [-0.15, -0.03] | -2.98 | 0.003
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | -0.10 | 0.03 | [-0.16, -0.04] | -3.11 | 0.002
> Social | Lie | -0.05 | 0.03 | [-0.12, 0.01] | -1.70 | 0.090
> Polygraph | Truth | 0.09 | 0.03 | [ 0.03, 0.16] | 2.94 | 0.003
> Social | Truth | 5.67e-03 | 0.03 | [-0.06, 0.07] | 0.18 | 0.859
> Marginal effects estimated for YONI_Physical
p_conf_yoni_physical <- plot_effect(model, var = "YONI_Physical", outcome = "Confidence")
# p_conf_yoni_physicalmodel <- glmmTMB(RT ~ Answer / (Condition * YONI_Physical) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | 3.56 | 1.08 | [ 1.44, 5.69] | 3.28 | 0.001
> Answer [Truth] | 1.18 | 0.34 | [ 0.51, 1.84] | 3.46 | < .001
> Answer [Lie] * ConditionSocial | 0.20 | 0.34 | [-0.46, 0.87] | 0.60 | 0.551
> Answer [Truth] * ConditionSocial | -0.85 | 0.34 | [-1.51, -0.18] | -2.49 | 0.013
> Answer [Lie] * YONI Physical | 0.07 | 0.09 | [-0.10, 0.24] | 0.82 | 0.414
> Answer [Truth] * YONI Physical | -0.02 | 0.09 | [-0.19, 0.15] | -0.23 | 0.820
> Answer [Lie] * ConditionSocial * YONI Physical | -0.06 | 0.03 | [-0.11, 0.00] | -2.13 | 0.033
> Answer [Truth] * ConditionSocial * YONI Physical | 0.03 | 0.03 | [-0.03, 0.08] | 1.01 | 0.312
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | 0.07 | 0.09 | [-0.10, 0.24] | 0.82 | 0.414
> Social | Lie | 0.01 | 0.09 | [-0.16, 0.18] | 0.15 | 0.883
> Polygraph | Truth | -0.02 | 0.09 | [-0.19, 0.15] | -0.23 | 0.820
> Social | Truth | 7.82e-03 | 0.09 | [-0.16, 0.18] | 0.09 | 0.929
> Marginal effects estimated for YONI_Physical
p_rt_yoni_physical <- plot_effect(model, var = "YONI_Physical", outcome = "RT")
# p_rt_yoni_physicalget_correlation <- function(var = "YONI_", var2 = "LIE_") {
r <- correlation(select(dfsub, starts_with(var2)),
select(dfsub, starts_with(var)),
p_adjust = "none") |>
mutate(Parameter1 = paste0(str_replace(Parameter1, "_", " ("), ")"),
Parameter2 = paste0(str_replace(Parameter2, "_", " ("), ")"))
p <- summary(r) |>
plot() +
theme_minimal()
list(r = r, plot = p)
}
r <- get_correlation(var = "YONI_")
r$plotp_conf_yoni_total /
p_conf_yoni_cognitive /
p_conf_yoni_affective /
p_conf_yoni_physical +
patchwork::plot_annotation(title = "Theory of Mind", theme = theme(plot.title = element_text(hjust = 0.5)))p_rt_yoni_total /
p_rt_yoni_cognitive /
p_rt_yoni_affective /
p_rt_yoni_physical +
patchwork::plot_annotation(title = "Theory of Mind", theme = theme(plot.title = element_text(hjust = 0.5)))model <- glmmTMB(Confidence ~ Answer / (Condition * BES_Total) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | 2.29 | 0.74 | [ 0.84, 3.73] | 3.10 | 0.002
> Answer [Truth] | -3.03 | 0.66 | [-4.31, -1.74] | -4.62 | < .001
> Answer [Lie] * ConditionSocial | -1.58 | 0.67 | [-2.91, -0.26] | -2.35 | 0.019
> Answer [Truth] * ConditionSocial | 1.00 | 0.67 | [-0.30, 2.31] | 1.51 | 0.131
> Answer [Lie] * BES Total | -0.03 | 9.77e-03 | [-0.05, -0.02] | -3.57 | < .001
> Answer [Truth] * BES Total | 0.02 | 9.86e-03 | [ 0.00, 0.04] | 2.28 | 0.022
> Answer [Lie] * ConditionSocial * BES Total | 0.02 | 8.92e-03 | [ 0.01, 0.04] | 2.54 | 0.011
> Answer [Truth] * ConditionSocial * BES Total | -0.01 | 8.81e-03 | [-0.03, 0.00] | -1.63 | 0.102
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> -------------------------------------------------------------------------------
> Polygraph | Lie | -0.03 | 9.77e-03 | [-0.05, -0.02] | -3.57 | < .001
> Social | Lie | -0.01 | 0.01 | [-0.03, 0.01] | -1.21 | 0.225
> Polygraph | Truth | 0.02 | 9.86e-03 | [ 0.00, 0.04] | 2.28 | 0.023
> Social | Truth | 8.11e-03 | 9.89e-03 | [-0.01, 0.03] | 0.82 | 0.413
> Marginal effects estimated for BES_Total
p_conf_bes_total <- plot_effect(model, var = "BES_Total", outcome = "Confidence")
# p_conf_bes_totalmodel <- glmmTMB(RT ~ Answer / (Condition * BES_Total) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------------------
> (Intercept) | 4.80 | 2.08 | [ 0.73, 8.87] | 2.31 | 0.021
> Answer [Truth] | 1.96 | 0.66 | [ 0.66, 3.25] | 2.97 | 0.003
> Answer [Lie] * ConditionSocial | 1.27 | 0.66 | [-0.02, 2.56] | 1.93 | 0.054
> Answer [Truth] * ConditionSocial | -1.16 | 0.66 | [-2.45, 0.13] | -1.76 | 0.078
> Answer [Lie] * BES Total | -5.05e-03 | 0.03 | [-0.06, 0.05] | -0.18 | 0.855
> Answer [Truth] * BES Total | -0.03 | 0.03 | [-0.08, 0.02] | -1.10 | 0.273
> Answer [Lie] * ConditionSocial * BES Total | -0.02 | 8.76e-03 | [-0.04, -0.01] | -2.72 | 0.007
> Answer [Truth] * ConditionSocial * BES Total | 8.68e-03 | 8.76e-03 | [-0.01, 0.03] | 0.99 | 0.322
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | -5.05e-03 | 0.03 | [-0.06, 0.05] | -0.18 | 0.855
> Social | Lie | -0.03 | 0.03 | [-0.08, 0.03] | -1.05 | 0.296
> Polygraph | Truth | -0.03 | 0.03 | [-0.08, 0.02] | -1.10 | 0.273
> Social | Truth | -0.02 | 0.03 | [-0.08, 0.03] | -0.78 | 0.435
> Marginal effects estimated for BES_Total
p_rt_bes_total <- plot_effect(model, var = "BES_Total", outcome = "RT")
# p_rt_bes_totalmodel <- glmmTMB(Confidence ~ Answer / (Condition * BES_Cognitive) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -----------------------------------------------------------------------------------------------------
> (Intercept) | 0.72 | 0.65 | [-0.55, 1.99] | 1.11 | 0.266
> Answer [Truth] | -0.36 | 0.58 | [-1.51, 0.78] | -0.62 | 0.533
> Answer [Lie] * ConditionSocial | -0.46 | 0.60 | [-1.63, 0.72] | -0.76 | 0.446
> Answer [Truth] * ConditionSocial | -0.31 | 0.58 | [-1.46, 0.83] | -0.54 | 0.591
> Answer [Lie] * BES Cognitive | -0.03 | 0.02 | [-0.07, 0.01] | -1.65 | 0.099
> Answer [Truth] * BES Cognitive | 0.02 | 0.02 | [-0.02, 0.05] | 0.92 | 0.358
> Answer [Lie] * ConditionSocial * BES Cognitive | 0.02 | 0.02 | [-0.02, 0.05] | 0.99 | 0.323
> Answer [Truth] * ConditionSocial * BES Cognitive | 6.44e-03 | 0.02 | [-0.03, 0.04] | 0.39 | 0.694
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | -0.03 | 0.02 | [-0.07, 0.01] | -1.65 | 0.099
> Social | Lie | -0.01 | 0.02 | [-0.05, 0.02] | -0.73 | 0.466
> Polygraph | Truth | 0.02 | 0.02 | [-0.02, 0.05] | 0.92 | 0.358
> Social | Truth | 0.02 | 0.02 | [-0.01, 0.06] | 1.27 | 0.206
> Marginal effects estimated for BES_Cognitive
p_conf_bes_cognitive <- plot_effect(model, var = "BES_Cognitive", outcome = "Confidence")
# p_conf_bes_cognitivemodel <- glmmTMB(RT ~ Answer / (Condition * BES_Cognitive) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | 5.43 | 1.75 | [ 2.00, 8.86] | 3.10 | 0.002
> Answer [Truth] | 1.13 | 0.57 | [ 0.02, 2.24] | 2.00 | 0.046
> Answer [Lie] * ConditionSocial | 2.01 | 0.57 | [ 0.90, 3.12] | 3.54 | < .001
> Answer [Truth] * ConditionSocial | 0.25 | 0.57 | [-0.87, 1.36] | 0.43 | 0.665
> Answer [Lie] * BES Cognitive | -0.03 | 0.05 | [-0.12, 0.07] | -0.58 | 0.562
> Answer [Truth] * BES Cognitive | -0.06 | 0.05 | [-0.15, 0.04] | -1.19 | 0.234
> Answer [Lie] * ConditionSocial * BES Cognitive | -0.07 | 0.02 | [-0.10, -0.04] | -4.47 | < .001
> Answer [Truth] * ConditionSocial * BES Cognitive | -0.02 | 0.02 | [-0.05, 0.01] | -1.35 | 0.178
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | -0.03 | 0.05 | [-0.12, 0.07] | -0.58 | 0.562
> Social | Lie | -0.10 | 0.05 | [-0.20, 0.00] | -2.03 | 0.043
> Polygraph | Truth | -0.06 | 0.05 | [-0.15, 0.04] | -1.19 | 0.234
> Social | Truth | -0.08 | 0.05 | [-0.18, 0.02] | -1.63 | 0.104
> Marginal effects estimated for BES_Cognitive
p_rt_bes_cognitive <- plot_effect(model, var = "BES_Cognitive", outcome = "RT")
# p_rt_bes_cognitivemodel <- glmmTMB(Confidence ~ Answer / (Condition * BES_Affective) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | 1.99 | 0.58 | [ 0.86, 3.12] | 3.46 | < .001
> Answer [Truth] | -2.60 | 0.52 | [-3.62, -1.59] | -5.03 | < .001
> Answer [Lie] * ConditionSocial | -1.50 | 0.53 | [-2.53, -0.46] | -2.84 | 0.005
> Answer [Truth] * ConditionSocial | 1.36 | 0.52 | [ 0.33, 2.38] | 2.59 | 0.010
> Answer [Lie] * BES Affective | -0.06 | 0.01 | [-0.09, -0.03] | -4.09 | < .001
> Answer [Truth] * BES Affective | 0.04 | 0.01 | [ 0.01, 0.07] | 2.70 | 0.007
> Answer [Lie] * ConditionSocial * BES Affective | 0.04 | 0.01 | [ 0.01, 0.07] | 3.10 | 0.002
> Answer [Truth] * ConditionSocial * BES Affective | -0.04 | 0.01 | [-0.06, -0.01] | -2.75 | 0.006
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> ---------------------------------------------------------------------------
> Polygraph | Lie | -0.06 | 0.01 | [-0.09, -0.03] | -4.09 | < .001
> Social | Lie | -0.02 | 0.01 | [-0.05, 0.01] | -1.21 | 0.225
> Polygraph | Truth | 0.04 | 0.01 | [ 0.01, 0.07] | 2.70 | 0.007
> Social | Truth | 3.24e-03 | 0.01 | [-0.03, 0.03] | 0.22 | 0.823
> Marginal effects estimated for BES_Affective
p_conf_bes_affective <- plot_effect(model, var = "BES_Affective", outcome = "Confidence")
# p_conf_bes_affectivemodel <- glmmTMB(RT ~ Answer / (Condition * BES_Affective) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | 4.13 | 1.63 | [ 0.93, 7.33] | 2.53 | 0.012
> Answer [Truth] | 1.44 | 0.51 | [ 0.44, 2.45] | 2.82 | 0.005
> Answer [Lie] * ConditionSocial | -0.30 | 0.51 | [-1.31, 0.70] | -0.59 | 0.554
> Answer [Truth] * ConditionSocial | -1.80 | 0.51 | [-2.80, -0.79] | -3.51 | < .001
> Answer [Lie] * BES Affective | 7.53e-03 | 0.04 | [-0.07, 0.09] | 0.18 | 0.854
> Answer [Truth] * BES Affective | -0.03 | 0.04 | [-0.11, 0.05] | -0.67 | 0.506
> Answer [Lie] * ConditionSocial * BES Affective | -5.15e-03 | 0.01 | [-0.03, 0.02] | -0.40 | 0.688
> Answer [Truth] * ConditionSocial * BES Affective | 0.03 | 0.01 | [ 0.01, 0.06] | 2.53 | 0.011
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | 7.53e-03 | 0.04 | [-0.07, 0.09] | 0.18 | 0.854
> Social | Lie | 2.38e-03 | 0.04 | [-0.08, 0.08] | 0.06 | 0.954
> Polygraph | Truth | -0.03 | 0.04 | [-0.11, 0.05] | -0.67 | 0.506
> Social | Truth | 5.28e-03 | 0.04 | [-0.07, 0.09] | 0.13 | 0.897
> Marginal effects estimated for BES_Affective
p_rt_bes_affective <- plot_effect(model, var = "BES_Affective", outcome = "RT")
# p_rt_bes_affectiver <- get_correlation(var = "BES_")
r$plotp_conf_bes_total /
p_conf_bes_cognitive /
p_conf_bes_affective +
patchwork::plot_annotation(title = "Empathy", theme = theme(plot.title = element_text(hjust = 0.5)))p_rt_bes_total /
p_rt_bes_cognitive /
p_rt_bes_affective +
patchwork::plot_annotation(title = "Empathy", theme = theme(plot.title = element_text(hjust = 0.5)))model <- glmmTMB(Confidence ~ Answer / (Condition * HCT_Accuracy) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------------------
> (Intercept) | -1.17 | 0.26 | [-1.68, -0.67] | -4.57 | < .001
> Answer [Truth] | 2.76 | 0.23 | [ 2.30, 3.22] | 11.86 | < .001
> Answer [Lie] * ConditionSocial | 0.62 | 0.23 | [ 0.16, 1.08] | 2.67 | 0.008
> Answer [Truth] * ConditionSocial | -0.59 | 0.23 | [-1.04, -0.14] | -2.56 | 0.010
> Answer [Lie] * HCT Accuracy | 1.37 | 0.40 | [ 0.59, 2.16] | 3.44 | < .001
> Answer [Truth] * HCT Accuracy | -1.06 | 0.40 | [-1.84, -0.28] | -2.68 | 0.007
> Answer [Lie] * ConditionSocial * HCT Accuracy | -0.81 | 0.36 | [-1.52, -0.09] | -2.21 | 0.027
> Answer [Truth] * ConditionSocial * HCT Accuracy | 0.85 | 0.36 | [ 0.15, 1.55] | 2.37 | 0.018
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> ---------------------------------------------------------------------------
> Polygraph | Lie | 1.37 | 0.40 | [ 0.59, 2.16] | 3.44 | < .001
> Social | Lie | 0.57 | 0.40 | [-0.22, 1.35] | 1.42 | 0.155
> Polygraph | Truth | -1.06 | 0.40 | [-1.84, -0.28] | -2.68 | 0.008
> Social | Truth | -0.21 | 0.40 | [-0.99, 0.57] | -0.53 | 0.595
> Marginal effects estimated for HCT_Accuracy
p_conf_hct_accuracy <- plot_effect(model, var = "HCT_Accuracy", outcome = "Confidence")model <- glmmTMB(RT ~ Answer / (Condition * HCT_Accuracy) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ----------------------------------------------------------------------------------------------------------
> (Intercept) | 4.87 | 0.70 | [ 3.49, 6.25] | 6.92 | < .001
> Answer [Truth] | -0.30 | 0.22 | [-0.74, 0.13] | -1.37 | 0.170
> Answer [Lie] * ConditionSocial | -0.51 | 0.22 | [-0.94, -0.07] | -2.28 | 0.022
> Answer [Truth] * ConditionSocial | -0.30 | 0.22 | [-0.73, 0.13] | -1.36 | 0.175
> Answer [Lie] * HCT Accuracy | -0.74 | 1.09 | [-2.88, 1.41] | -0.67 | 0.501
> Answer [Truth] * HCT Accuracy | -0.12 | 1.09 | [-2.26, 2.02] | -0.11 | 0.915
> Answer [Lie] * ConditionSocial * HCT Accuracy | -1.95e-03 | 0.34 | [-0.68, 0.67] | -5.65e-03 | 0.995
> Answer [Truth] * ConditionSocial * HCT Accuracy | -0.35 | 0.34 | [-1.02, 0.33] | -1.01 | 0.312
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | -0.74 | 1.09 | [-2.88, 1.41] | -0.67 | 0.501
> Social | Lie | -0.74 | 1.09 | [-2.88, 1.40] | -0.68 | 0.500
> Polygraph | Truth | -0.12 | 1.09 | [-2.26, 2.03] | -0.11 | 0.915
> Social | Truth | -0.47 | 1.09 | [-2.61, 1.68] | -0.43 | 0.670
> Marginal effects estimated for HCT_Accuracy
p_rt_hct_accuracy <- plot_effect(model, var = "HCT_Accuracy", outcome = "RT")model <- glmmTMB(Confidence ~ Answer / (Condition * HCT_Confidence) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> --------------------------------------------------------------------------------------------------------
> (Intercept) | -0.90 | 0.17 | [-1.23, -0.58] | -5.39 | < .001
> Answer [Truth] | 1.88 | 0.16 | [ 1.57, 2.20] | 11.60 | < .001
> Answer [Lie] * ConditionSocial | 0.45 | 0.16 | [ 0.13, 0.77] | 2.75 | 0.006
> Answer [Truth] * ConditionSocial | -0.40 | 0.16 | [-0.71, -0.08] | -2.48 | 0.013
> Answer [Lie] * HCT Confidence | 1.11 | 0.29 | [ 0.54, 1.69] | 3.80 | < .001
> Answer [Truth] * HCT Confidence | -0.07 | 0.29 | [-0.64, 0.50] | -0.25 | 0.804
> Answer [Lie] * ConditionSocial * HCT Confidence | -0.63 | 0.29 | [-1.19, -0.06] | -2.17 | 0.030
> Answer [Truth] * ConditionSocial * HCT Confidence | 0.63 | 0.28 | [ 0.08, 1.19] | 2.24 | 0.025
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | 1.11 | 0.29 | [ 0.54, 1.69] | 3.80 | < .001
> Social | Lie | 0.49 | 0.30 | [-0.10, 1.07] | 1.64 | 0.101
> Polygraph | Truth | -0.07 | 0.29 | [-0.64, 0.50] | -0.25 | 0.804
> Social | Truth | 0.56 | 0.29 | [-0.02, 1.14] | 1.91 | 0.056
> Marginal effects estimated for HCT_Confidence
p_conf_hct_confidence <- plot_effect(model, var = "HCT_Confidence", outcome = "Confidence")model <- glmmTMB(RT ~ Answer / (Condition * HCT_Confidence) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> --------------------------------------------------------------------------------------------------------
> (Intercept) | 5.41 | 0.45 | [ 4.53, 6.28] | 12.08 | < .001
> Answer [Truth] | 0.03 | 0.15 | [-0.28, 0.33] | 0.17 | 0.868
> Answer [Lie] * ConditionSocial | -0.71 | 0.15 | [-1.01, -0.41] | -4.64 | < .001
> Answer [Truth] * ConditionSocial | -0.47 | 0.15 | [-0.77, -0.17] | -3.08 | 0.002
> Answer [Lie] * HCT Confidence | -1.96 | 0.78 | [-3.49, -0.43] | -2.51 | 0.012
> Answer [Truth] * HCT Confidence | -1.86 | 0.78 | [-3.40, -0.33] | -2.39 | 0.017
> Answer [Lie] * ConditionSocial * HCT Confidence | 0.41 | 0.27 | [-0.12, 0.94] | 1.52 | 0.129
> Answer [Truth] * ConditionSocial * HCT Confidence | -0.08 | 0.27 | [-0.61, 0.45] | -0.29 | 0.769
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | -1.96 | 0.78 | [-3.49, -0.43] | -2.51 | 0.012
> Social | Lie | -1.55 | 0.78 | [-3.08, -0.01] | -1.98 | 0.048
> Polygraph | Truth | -1.86 | 0.78 | [-3.40, -0.33] | -2.39 | 0.017
> Social | Truth | -1.94 | 0.78 | [-3.48, -0.41] | -2.49 | 0.013
> Marginal effects estimated for HCT_Confidence
p_rt_hct_confidence <- plot_effect(model, var = "HCT_Confidence", outcome = "RT")model <- glmmTMB(Confidence ~ Answer / (Condition * HCT_Awareness) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | -0.35 | 0.08 | [-0.52, -0.19] | -4.15 | < .001
> Answer [Truth] | 1.31 | 0.08 | [ 1.16, 1.46] | 16.82 | < .001
> Answer [Lie] * ConditionSocial | 0.14 | 0.08 | [-0.01, 0.29] | 1.83 | 0.067
> Answer [Truth] * ConditionSocial | -0.09 | 0.08 | [-0.24, 0.06] | -1.14 | 0.254
> Answer [Lie] * HCT Awareness | -0.60 | 0.14 | [-0.87, -0.33] | -4.35 | < .001
> Answer [Truth] * HCT Awareness | 0.19 | 0.14 | [-0.08, 0.46] | 1.40 | 0.161
> Answer [Lie] * ConditionSocial * HCT Awareness | 0.58 | 0.13 | [ 0.33, 0.83] | 4.52 | < .001
> Answer [Truth] * ConditionSocial * HCT Awareness | -3.67e-03 | 0.13 | [-0.25, 0.24] | -0.03 | 0.977
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> ---------------------------------------------------------------------------
> Polygraph | Lie | -0.60 | 0.14 | [-0.87, -0.33] | -4.35 | < .001
> Social | Lie | -0.03 | 0.14 | [-0.30, 0.25] | -0.19 | 0.846
> Polygraph | Truth | 0.19 | 0.14 | [-0.08, 0.46] | 1.40 | 0.161
> Social | Truth | 0.19 | 0.14 | [-0.08, 0.46] | 1.37 | 0.171
> Marginal effects estimated for HCT_Awareness
p_conf_hct_awareness <- plot_effect(model, var = "HCT_Awareness", outcome = "Confidence")model <- glmmTMB(RT ~ Answer / (Condition * HCT_Awareness) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | 4.45 | 0.22 | [ 4.01, 4.88] | 19.96 | < .001
> Answer [Truth] | 0.07 | 0.07 | [-0.07, 0.21] | 0.93 | 0.350
> Answer [Lie] * ConditionSocial | -0.51 | 0.07 | [-0.65, -0.37] | -7.16 | < .001
> Answer [Truth] * ConditionSocial | -0.51 | 0.07 | [-0.65, -0.37] | -7.16 | < .001
> Answer [Lie] * HCT Awareness | 0.92 | 0.35 | [ 0.22, 1.61] | 2.58 | 0.010
> Answer [Truth] * HCT Awareness | 0.70 | 0.35 | [ 0.01, 1.40] | 1.98 | 0.047
> Answer [Lie] * ConditionSocial * HCT Awareness | -0.32 | 0.12 | [-0.55, -0.08] | -2.66 | 0.008
> Answer [Truth] * ConditionSocial * HCT Awareness | -0.08 | 0.12 | [-0.31, 0.16] | -0.64 | 0.524
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | 0.92 | 0.35 | [ 0.22, 1.61] | 2.58 | 0.010
> Social | Lie | 0.60 | 0.35 | [-0.10, 1.29] | 1.68 | 0.093
> Polygraph | Truth | 0.70 | 0.35 | [ 0.01, 1.40] | 1.98 | 0.047
> Social | Truth | 0.63 | 0.35 | [-0.07, 1.32] | 1.77 | 0.077
> Marginal effects estimated for HCT_Awareness
p_rt_hct_awareness <- plot_effect(model, var = "HCT_Awareness", outcome = "RT")r <- get_correlation(var = "HCT_")
r$plot# plot(correlation::cor_test(dfsub, "HCT_Accuracy", "LIE_Ability"))p_conf_hct_accuracy /
p_conf_hct_confidence /
p_conf_hct_awareness +
patchwork::plot_annotation(title = "Interoception", theme = theme(plot.title = element_text(hjust = 0.5)))p_rt_hct_accuracy /
p_rt_hct_confidence /
p_rt_hct_awareness +
patchwork::plot_annotation(title = "Interoception", theme = theme(plot.title = element_text(hjust = 0.5)))model <- glmmTMB(Confidence ~ Answer / (Condition * MAIA_Total) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ----------------------------------------------------------------------------------------------------
> (Intercept) | -2.39 | 0.40 | [-3.17, -1.60] | -5.97 | < .001
> Answer [Truth] | 3.93 | 0.37 | [ 3.20, 4.66] | 10.50 | < .001
> Answer [Lie] * ConditionSocial | 1.48 | 0.38 | [ 0.73, 2.23] | 3.85 | < .001
> Answer [Truth] * ConditionSocial | -0.93 | 0.38 | [-1.67, -0.19] | -2.45 | 0.014
> Answer [Lie] * MAIA Total | 0.75 | 0.14 | [ 0.47, 1.04] | 5.23 | < .001
> Answer [Truth] * MAIA Total | -0.22 | 0.14 | [-0.50, 0.06] | -1.54 | 0.124
> Answer [Lie] * ConditionSocial * MAIA Total | -0.50 | 0.14 | [-0.77, -0.23] | -3.60 | < .001
> Answer [Truth] * ConditionSocial * MAIA Total | 0.31 | 0.14 | [ 0.05, 0.58] | 2.30 | 0.022
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | 0.75 | 0.14 | [ 0.47, 1.04] | 5.23 | < .001
> Social | Lie | 0.26 | 0.15 | [-0.03, 0.54] | 1.76 | 0.079
> Polygraph | Truth | -0.22 | 0.14 | [-0.50, 0.06] | -1.54 | 0.124
> Social | Truth | 0.09 | 0.15 | [-0.19, 0.38] | 0.64 | 0.521
> Marginal effects estimated for MAIA_Total
p_conf_maia_total <- plot_effect(model, var = "MAIA_Total", outcome = "Confidence")model <- glmmTMB(RT ~ Answer / (Condition * MAIA_Total) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ----------------------------------------------------------------------------------------------------
> (Intercept) | 7.47 | 1.07 | [ 5.38, 9.56] | 6.99 | < .001
> Answer [Truth] | -0.19 | 0.36 | [-0.90, 0.52] | -0.53 | 0.596
> Answer [Lie] * ConditionSocial | -2.21 | 0.36 | [-2.92, -1.50] | -6.12 | < .001
> Answer [Truth] * ConditionSocial | -1.65 | 0.36 | [-2.36, -0.94] | -4.57 | < .001
> Answer [Lie] * MAIA Total | -1.12 | 0.38 | [-1.87, -0.37] | -2.91 | 0.004
> Answer [Truth] * MAIA Total | -1.02 | 0.38 | [-1.78, -0.27] | -2.66 | 0.008
> Answer [Lie] * ConditionSocial * MAIA Total | 0.63 | 0.13 | [ 0.37, 0.88] | 4.82 | < .001
> Answer [Truth] * ConditionSocial * MAIA Total | 0.42 | 0.13 | [ 0.16, 0.67] | 3.22 | 0.001
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | -1.12 | 0.38 | [-1.87, -0.37] | -2.91 | 0.004
> Social | Lie | -0.49 | 0.38 | [-1.25, 0.26] | -1.28 | 0.200
> Polygraph | Truth | -1.02 | 0.38 | [-1.78, -0.27] | -2.66 | 0.008
> Social | Truth | -0.60 | 0.38 | [-1.36, 0.15] | -1.57 | 0.116
> Marginal effects estimated for MAIA_Total
p_rt_maia_total <- plot_effect(model, var = "MAIA_Total", outcome = "RT")model <- glmmTMB(Confidence ~ Answer / (Condition * MAIA_Noticing) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | -1.64 | 0.37 | [-2.37, -0.92] | -4.45 | < .001
> Answer [Truth] | 3.44 | 0.32 | [ 2.81, 4.08] | 10.69 | < .001
> Answer [Lie] * ConditionSocial | 1.70 | 0.34 | [ 1.03, 2.36] | 5.03 | < .001
> Answer [Truth] * ConditionSocial | -0.57 | 0.33 | [-1.22, 0.08] | -1.71 | 0.087
> Answer [Lie] * MAIA Noticing | 0.39 | 0.11 | [ 0.18, 0.60] | 3.65 | < .001
> Answer [Truth] * MAIA Noticing | -0.25 | 0.11 | [-0.47, -0.04] | -2.34 | 0.019
> Answer [Lie] * ConditionSocial * MAIA Noticing | -0.47 | 0.10 | [-0.66, -0.28] | -4.80 | < .001
> Answer [Truth] * ConditionSocial * MAIA Noticing | 0.15 | 0.10 | [-0.04, 0.33] | 1.52 | 0.130
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> ---------------------------------------------------------------------------
> Polygraph | Lie | 0.39 | 0.11 | [ 0.18, 0.60] | 3.65 | < .001
> Social | Lie | -0.08 | 0.11 | [-0.30, 0.14] | -0.70 | 0.485
> Polygraph | Truth | -0.25 | 0.11 | [-0.47, -0.04] | -2.34 | 0.019
> Social | Truth | -0.11 | 0.11 | [-0.32, 0.11] | -0.99 | 0.325
> Marginal effects estimated for MAIA_Noticing
p_conf_maia_noticing <- plot_effect(model, var = "MAIA_Noticing", outcome = "Confidence")model <- glmmTMB(RT ~ Answer / (Condition * MAIA_Noticing) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------
> (Intercept) | 6.72 | 1.03 | [ 4.70, 8.73] | 6.52 | < .001
> Answer [Truth] | -0.98 | 0.33 | [-1.64, -0.33] | -2.96 | 0.003
> Answer [Lie] * ConditionSocial | -1.92 | 0.33 | [-2.57, -1.26] | -5.76 | < .001
> Answer [Truth] * ConditionSocial | -0.75 | 0.33 | [-1.40, -0.10] | -2.25 | 0.024
> Answer [Lie] * MAIA Noticing | -0.68 | 0.30 | [-1.26, -0.10] | -2.28 | 0.022
> Answer [Truth] * MAIA Noticing | -0.36 | 0.30 | [-0.94, 0.22] | -1.23 | 0.218
> Answer [Lie] * ConditionSocial * MAIA Noticing | 0.42 | 0.10 | [ 0.23, 0.60] | 4.34 | < .001
> Answer [Truth] * ConditionSocial * MAIA Noticing | 0.07 | 0.10 | [-0.12, 0.26] | 0.73 | 0.465
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | -0.68 | 0.30 | [-1.26, -0.10] | -2.28 | 0.022
> Social | Lie | -0.26 | 0.30 | [-0.84, 0.32] | -0.88 | 0.379
> Polygraph | Truth | -0.36 | 0.30 | [-0.94, 0.22] | -1.23 | 0.218
> Social | Truth | -0.29 | 0.30 | [-0.87, 0.29] | -0.99 | 0.320
> Marginal effects estimated for MAIA_Noticing
p_rt_maia_noticing <- plot_effect(model, var = "MAIA_Noticing", outcome = "RT")model <- glmmTMB(Confidence ~ Answer / (Condition * MAIA_NotDistracting) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------------
> (Intercept) | -0.79 | 0.17 | [-1.12, -0.45] | -4.60 | < .001
> Answer [Truth] | 1.63 | 0.16 | [ 1.31, 1.95] | 10.02 | < .001
> Answer [Lie] * ConditionSocial | 0.32 | 0.16 | [ 0.01, 0.64] | 2.00 | 0.046
> Answer [Truth] * ConditionSocial | 2.72e-03 | 0.16 | [-0.31, 0.32] | 0.02 | 0.986
> Answer [Lie] * MAIA NotDistracting | 0.27 | 0.09 | [ 0.09, 0.45] | 2.95 | 0.003
> Answer [Truth] * MAIA NotDistracting | 0.06 | 0.09 | [-0.11, 0.24] | 0.70 | 0.483
> Answer [Lie] * ConditionSocial * MAIA NotDistracting | -0.11 | 0.09 | [-0.28, 0.06] | -1.30 | 0.194
> Answer [Truth] * ConditionSocial * MAIA NotDistracting | -0.05 | 0.09 | [-0.22, 0.11] | -0.63 | 0.527
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | 0.27 | 0.09 | [ 0.09, 0.45] | 2.95 | 0.003
> Social | Lie | 0.16 | 0.09 | [-0.02, 0.34] | 1.71 | 0.087
> Polygraph | Truth | 0.06 | 0.09 | [-0.11, 0.24] | 0.70 | 0.483
> Social | Truth | 9.67e-03 | 0.09 | [-0.17, 0.19] | 0.11 | 0.915
> Marginal effects estimated for MAIA_NotDistracting
p_conf_maia_notdistracting <- plot_effect(model, var = "MAIA_NotDistracting", outcome = "Confidence")model <- glmmTMB(RT ~ Answer / (Condition * MAIA_NotDistracting) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> -------------------------------------------------------------------------------------------------------------
> (Intercept) | 4.60 | 0.49 | [ 3.64, 5.56] | 9.38 | < .001
> Answer [Truth] | -0.07 | 0.15 | [-0.37, 0.23] | -0.46 | 0.645
> Answer [Lie] * ConditionSocial | -0.49 | 0.15 | [-0.79, -0.19] | -3.23 | 0.001
> Answer [Truth] * ConditionSocial | -0.23 | 0.15 | [-0.53, 0.07] | -1.49 | 0.137
> Answer [Lie] * MAIA NotDistracting | -0.11 | 0.26 | [-0.62, 0.40] | -0.41 | 0.680
> Answer [Truth] * MAIA NotDistracting | -0.02 | 0.26 | [-0.53, 0.49] | -0.08 | 0.936
> Answer [Lie] * ConditionSocial * MAIA NotDistracting | -7.52e-03 | 0.08 | [-0.17, 0.15] | -0.09 | 0.927
> Answer [Truth] * ConditionSocial * MAIA NotDistracting | -0.17 | 0.08 | [-0.34, -0.01] | -2.10 | 0.036
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> -------------------------------------------------------------------------
> Polygraph | Lie | -0.11 | 0.26 | [-0.62, 0.41] | -0.41 | 0.680
> Social | Lie | -0.12 | 0.26 | [-0.63, 0.40] | -0.44 | 0.659
> Polygraph | Truth | -0.02 | 0.26 | [-0.53, 0.49] | -0.08 | 0.936
> Social | Truth | -0.19 | 0.26 | [-0.71, 0.32] | -0.74 | 0.458
> Marginal effects estimated for MAIA_NotDistracting
p_rt_maia_notdistracting <- plot_effect(model, var = "MAIA_NotDistracting", outcome = "RT")model <- glmmTMB(Confidence ~ Answer / (Condition * MAIA_BodyListening) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------------------------
> (Intercept) | -1.26 | 0.20 | [-1.64, -0.87] | -6.41 | < .001
> Answer [Truth] | 2.25 | 0.19 | [ 1.89, 2.62] | 12.15 | < .001
> Answer [Lie] * ConditionSocial | 0.79 | 0.19 | [ 0.42, 1.15] | 4.22 | < .001
> Answer [Truth] * ConditionSocial | -0.12 | 0.18 | [-0.47, 0.24] | -0.63 | 0.526
> Answer [Lie] * MAIA BodyListening | 0.36 | 0.07 | [ 0.22, 0.49] | 5.13 | < .001
> Answer [Truth] * MAIA BodyListening | -0.02 | 0.07 | [-0.15, 0.12] | -0.25 | 0.802
> Answer [Lie] * ConditionSocial * MAIA BodyListening | -0.26 | 0.07 | [-0.39, -0.13] | -3.85 | < .001
> Answer [Truth] * ConditionSocial * MAIA BodyListening | 0.01 | 0.06 | [-0.12, 0.14] | 0.18 | 0.855
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1980) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | 0.36 | 0.07 | [ 0.22, 0.49] | 5.13 | < .001
> Social | Lie | 0.10 | 0.07 | [-0.04, 0.24] | 1.43 | 0.153
> Polygraph | Truth | -0.02 | 0.07 | [-0.15, 0.12] | -0.25 | 0.802
> Social | Truth | -5.43e-03 | 0.07 | [-0.14, 0.13] | -0.08 | 0.937
> Marginal effects estimated for MAIA_BodyListening
p_conf_maia_bodylistening <- plot_effect(model, var = "MAIA_BodyListening", outcome = "Confidence")model <- glmmTMB(RT ~ Answer / (Condition * MAIA_BodyListening) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params> # Fixed Effects
>
> Parameter | Coefficient | SE | 95% CI | z | p
> ------------------------------------------------------------------------------------------------------------
> (Intercept) | 5.85 | 0.53 | [ 4.81, 6.89] | 11.04 | < .001
> Answer [Truth] | -0.03 | 0.18 | [-0.38, 0.31] | -0.19 | 0.847
> Answer [Lie] * ConditionSocial | -1.36 | 0.18 | [-1.71, -1.01] | -7.69 | < .001
> Answer [Truth] * ConditionSocial | -1.19 | 0.18 | [-1.54, -0.84] | -6.73 | < .001
> Answer [Lie] * MAIA BodyListening | -0.55 | 0.19 | [-0.92, -0.19] | -2.96 | 0.003
> Answer [Truth] * MAIA BodyListening | -0.51 | 0.19 | [-0.88, -0.15] | -2.74 | 0.006
> Answer [Lie] * ConditionSocial * MAIA BodyListening | 0.33 | 0.06 | [ 0.21, 0.45] | 5.27 | < .001
> Answer [Truth] * ConditionSocial * MAIA BodyListening | 0.26 | 0.06 | [ 0.14, 0.39] | 4.19 | < .001
results$marginal_effects> Estimated Marginal Effects
>
> Condition | Answer | Coefficient | SE | 95% CI | t(1989) | p
> --------------------------------------------------------------------------
> Polygraph | Lie | -0.55 | 0.19 | [-0.92, -0.19] | -2.96 | 0.003
> Social | Lie | -0.22 | 0.19 | [-0.59, 0.14] | -1.19 | 0.235
> Polygraph | Truth | -0.51 | 0.19 | [-0.88, -0.15] | -2.74 | 0.006
> Social | Truth | -0.25 | 0.19 | [-0.62, 0.12] | -1.33 | 0.183
> Marginal effects estimated for MAIA_BodyListening
p_rt_maia_bodylistening <- plot_effect(model, var = "MAIA_BodyListening", outcome = "RT")r <- get_correlation(var = "MAIA_")
r$plot +
theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1))p_conf_maia_total /
p_conf_maia_noticing /
p_conf_maia_notdistracting /
p_conf_maia_bodylistening +
patchwork::plot_annotation(title = "Interoception (MAIA)", theme = theme(plot.title = element_text(hjust = 0.5)))p_rt_maia_total /
p_rt_maia_noticing /
p_rt_maia_notdistracting /
p_rt_maia_bodylistening +
patchwork::plot_annotation(title = "Interoception (MAIA)", theme = theme(plot.title = element_text(hjust = 0.5)))The full script of executive code contained in this document is reproduced here.
# Set up the environment (or use local alternative `source("utils/config.R")`)
source("https://raw.githubusercontent.com/RealityBending/TemplateResults/main/utils/config.R")
options(dplyr.summarise.inform = FALSE)
knitr::opts_chunk$set(echo = TRUE)
library(ggplot2)
theme_set(see::theme_modern())
# This chunk is a bit complex so don't worry about it: it's made to add badges to the HTML versions
# NOTE: You have to replace the links accordingly to have working "buttons" on the HTML versions
if (!knitr::is_latex_output() && knitr::is_html_output()) {
cat("
[](https://github.com/RealityBending/TemplateResults)
[](https://realitybending.github.io/TemplateResults/)
[](https://github.com/RealityBending/TemplateResults/raw/main/word_and_pdf/SupplementaryMaterials.docx)
[](https://github.com/RealityBending/TemplateResults/blob/main/word_and_pdf/SupplementaryMaterials.pdf)")
}
library(tidyverse)
library(patchwork)
library(glmmTMB)
library(report)
library(parameters)
library(correlation)
library(modelbased)
library(performance)
library(see)
summary(report::report(sessionInfo()))
# setwd("C:/Users/user/Desktop/Sputnik/2019-23/DeceptionInteroTom")
df <- read.csv("data/data_combined.csv") %>%
mutate(ID = as.factor(paste0("S", ID)),
condition = as.factor(condition),
item = as.factor(item),
style = as.factor(style),
instruction = as.factor(instruction)) |>
#TODO: This renaming should be done at the preprocessing stage
rename("Participant" = "ID",
"Condition" = "condition",
"Item" = "item",
"Phrasing" = "style",
"Answer" = "instruction",
"YONI_Total" = "yoni_total",
"YONI_Affective" = "yoni_affective",
"YONI_Cognitive" = "yoni_cognitive",
"YONI_Physical" = "yoni_physical",
"BES_Total" = "BES_total",
"BES_Cognitive" = "BES_cognitive",
"BES_Affective" = "BES_affective",
"HCT_Confidence" = "HCT_confidence",
"HCT_Accuracy" = "HCT_accuracy",
"HCT_Awareness" = "HCT_awareness",
"MAIA_Total" = "MAIA_total",
"MAIA_AttentionRegulation" = "MAIA_attention_regulation",
"MAIA_BodyListening" = "MAIA_body_listening",
"MAIA_EmotionalAwareness" = "MAIA_emotional_awareness",
"MAIA_NotDistracting" = "MAIA_not_distracting",
"MAIA_NotWorrying" = "MAIA_not_worrying",
"MAIA_Noticing" = "MAIA_noticing",
"MAIA_SelfRegulation" = "MAIA_self_regulation",
"MAIA_Trusting" = "MAIA_trusting",
"LIE_Ability" = "lie_ability",
"LIE_Frequency" = "lie_frequency",
"LIE_Negativity" = "lie_negativity",
"LIE_Contextuality" = "lie_contextuality",
"Confidence" = "DT_confidence",
"RT" = "DT_RT") |>
mutate(Answer = fct_recode(Answer, Lie = "LIE", Truth = "TRUTH")) |>
select(-HCT_guess, -HCT_noguess, -HCT_onebreath)
cat(paste("The data consists of",
report::report_participants(df,
participants = "Participant",
sex = "Gender",
age = "Age")))
report::cite_packages(sessionInfo())
df %>%
group_by(Participant) %>%
select(starts_with("YONI_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_manual(values = c("YONI (Affective)" = "Purple",
"YONI (Cognitive)" = "Blue",
"YONI (Physical)" = "Green",
"YONI (Total)"= "DarkBlue"),
guide = "none") +
facet_wrap(~name, scales = "free")
df %>%
group_by(Participant) %>%
select(starts_with("BES_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_manual(values = c("BES (Affective)" = "Purple",
"BES (Cognitive)" = "Blue",
"BES (Total)"= "DarkBlue"),
guide = "none") +
facet_wrap(~name, scales = "free")
df %>%
group_by(Participant) %>%
select(starts_with("HCT_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_manual(values = c("HCT (Accuracy)" = "Red",
"HCT (Awareness)" = "Orange",
"HCT (Confidence)"= "DarkOrange"),
guide = "none") +
facet_wrap(~name, scales = "free")
df %>%
group_by(Participant) %>%
select(starts_with("MAIA_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_brewer(palette = "Reds", guide = "none") +
facet_wrap(~name, scales = "free")
df %>%
group_by(Participant) %>%
select(starts_with("LIE_")) |>
summarise_all(mean, na.rm=TRUE) |>
tidyr::pivot_longer(-Participant, values_to = "Scores") |>
mutate(name = paste0(str_replace(name, "_", " ("), ")")) |>
ggplot(aes(x = Scores, fill = name)) +
geom_density() +
scale_fill_manual(values = c("LIE (Ability)" = "#2196F3",
"LIE (Frequency)" = "#4CAF50",
"LIE (Contextuality)"= "#FF9800",
"LIE (Negativity)"= "#E91E63"),
guide = "none") +
facet_wrap(~name, scales = "free")
df |>
group_by(Participant, Answer) |>
summarise(Confidence = paste(insight::format_value(mean(Confidence, na.rm = TRUE)),
" +- ",
insight::format_value(sd(Confidence, na.rm = TRUE))),
RT = paste(insight::format_value(mean(RT, na.rm = TRUE)),
" +- ",
insight::format_value(sd(RT, na.rm = TRUE)))) |>
arrange(Participant) |>
knitr::kable()
df <- df |>
dplyr::filter(Participant != "S9", # Extreme answers
!Participant %in% c("S3", "S15", "S19", "S23")) # No data
p1 <- df |>
dplyr::filter(!Participant %in% c("S29")) |>
ggplot(aes(x = Confidence, fill = Participant)) +
geom_density(alpha = 0.1) +
see::scale_fill_material_d(palette = "rainbow", guide = "none") +
see::theme_modern() +
scale_x_continuous(labels = scales::percent, expand=expansion(c(0, .05))) +
scale_y_continuous(expand=expansion(c(0, .05))) +
facet_wrap(~Answer)
p2 <- df |>
dplyr::filter(!Participant %in% c("S29")) |>
ggplot(aes(x = RT, fill = Participant)) +
geom_density(alpha = 0.1) +
see::scale_fill_material_d(palette = "rainbow", guide = "none") +
scale_x_continuous(expand=expansion(c(0, .05))) +
scale_y_continuous(expand=expansion(c(0, .05))) +
facet_wrap(~Answer)
p1 / p2
dfsub <- df |>
select(Participant,
starts_with("YONI_"),
starts_with("BES_"),
starts_with("HCT_"),
starts_with("MAIA_"),
starts_with("LIE_")) |>
group_by(Participant) |>
summarise_all(mean)
r <- correlation(select(dfsub, starts_with("YONI_")),
select(dfsub, starts_with("BES_")),
p_adjust = "none")
summary(r) |>
plot()
r <- correlation(select(dfsub, starts_with("MAIA_")),
select(dfsub, starts_with("HCT_")),
p_adjust = "none")
summary(r) |>
plot()
r <- correlation(select(dfsub, starts_with(c("MAIA_", "HCT_"))),
select(dfsub, starts_with(c("YONI_", "BES_"))),
p_adjust = "none")
summary(r) |>
plot()
model <- glmmTMB(RT ~ Answer * Phrasing + (1|Participant) + (1|Item), data = df)
parameters::parameters(model, effects = "fixed")
estimate_means(model, at = c("Answer", "Phrasing")) |>
plot(show_data = "none")
model <- glmmTMB(Confidence ~ Answer * Phrasing + (1|Participant) + (1|Item), data = df)
parameters::parameters(model)
estimate_means(model, at = c("Answer", "Phrasing")) |>
plot(show_data = "none")
# Adjustments for beta models
df$Confidence[df$Confidence == 1] <- 0.99999
df$Confidence[df$Confidence == 0] <- 0.00001
model <- glmmTMB(Confidence ~ RT * Answer + Phrasing + (1|Participant) + (1|Item),
data = df, family = beta_family())
parameters::parameters(model, effects = "fixed")
estimate_relation(model, at = c("RT", "Answer")) |>
plot(length = 50, point = list(alpha = 0.3, size = 3.5))
model <- glmmTMB(Confidence ~ Answer * Condition + (1|Participant) + (1|Item),
data = df, family = beta_family())
parameters::parameters(model, effects = "fixed")
estimate_means(model, at = c("Condition", "Answer")) |>
plot(show_data = "none")
model <- glmmTMB(RT ~ Answer * Condition + (1|Participant) + (1|Item),
data = df)
parameters::parameters(model, effects = "fixed")
estimate_means(model, at = c("Condition", "Answer")) |>
plot(show_data = "none")
model <- glmmTMB(Confidence ~ Answer / (Condition * YONI_Total) + (1|Participant) + (1|Item),
data = df, family = beta_family())
get_parameters <- function(model) {
# Parameters
params <- parameters::parameters(model, effects = "fixed")
# Marginal effects
at <- c("Answer", "Condition")
trend <- insight::find_predictors(model)$conditional
trend <- trend[!trend %in% at]
marg <- modelbased::estimate_slopes(model, trend = trend, at = at)
# Output
list(params = params, marginal_effects = marg)
}
results <- get_parameters(model)
results$params
results$marginal_effects
plot_effect <- function(model, var = "YONI_Total", outcome = "Confidence") {
data <- df |>
group_by(Participant, Answer, Condition) |>
summarise({{var}} := mean(.data[[var]], na.rm = TRUE),
SD = sd(.data[[outcome]], na.rm = TRUE),
{{outcome}} := mean(.data[[outcome]], na.rm = TRUE),
CI_low = .data[[outcome]] - SD / 2,
CI_high = .data[[outcome]] + SD / 2)
dodge_width <- 0.02 * diff(range(data[[var]]))
ylab <- ifelse(outcome == "RT", "Reaction Time (s)", "Confidence")
link_data <- estimate_relation(model, at = c("Condition", var, "Answer"), length = 30)
ggplot(link_data, aes_string(x = var, y = "Predicted")) +
geom_pointrange(data = data, aes_string(y = outcome, color = "Condition", ymin = "CI_low", ymax = "CI_high"), position = position_dodge(width = dodge_width)) +
geom_ribbon(aes(ymin = CI_low, ymax = CI_high, fill = Condition), alpha = 0.33) +
geom_line(aes(color = Condition)) +
labs(y = ylab, x = paste0(stringr::str_replace(var, "_", " ("), ")")) +
scale_color_manual(values = c("Polygraph" = "#FF5722", "Social" = "#2196F3")) +
scale_fill_manual(values = c("Polygraph" = "#FF5722", "Social" = "#2196F3")) +
facet_wrap(~Answer)
}
p_conf_yoni_total <- plot_effect(model, var = "YONI_Total", outcome = "Confidence")
# p_conf_yoni_total
model <- glmmTMB(RT ~ Answer / (Condition * YONI_Total) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_yoni_total <- plot_effect(model, var = "YONI_Total", outcome = "RT")
# p_rt_yoni_total
model <- glmmTMB(Confidence ~ Answer / (Condition * YONI_Cognitive) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_yoni_cognitive <- plot_effect(model, var = "YONI_Cognitive", outcome = "Confidence")
# p_conf_yoni_cognitive
model <- glmmTMB(RT ~ Answer / (Condition * YONI_Cognitive) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_yoni_cognitive <- plot_effect(model, var = "YONI_Cognitive", outcome = "RT")
# p_rt_yoni_cognitive
model <- glmmTMB(Confidence ~ Answer / (Condition * YONI_Affective) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_yoni_affective <- plot_effect(model, var = "YONI_Affective", outcome = "Confidence")
# p_conf_yoni_affective
model <- glmmTMB(RT ~ Answer / (Condition * YONI_Affective) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_yoni_affective <- plot_effect(model, var = "YONI_Affective", outcome = "RT")
# p_rt_yoni_affective
model <- glmmTMB(Confidence ~ Answer / (Condition * YONI_Physical) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_yoni_physical <- plot_effect(model, var = "YONI_Physical", outcome = "Confidence")
# p_conf_yoni_physical
model <- glmmTMB(RT ~ Answer / (Condition * YONI_Physical) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_yoni_physical <- plot_effect(model, var = "YONI_Physical", outcome = "RT")
# p_rt_yoni_physical
get_correlation <- function(var = "YONI_", var2 = "LIE_") {
r <- correlation(select(dfsub, starts_with(var2)),
select(dfsub, starts_with(var)),
p_adjust = "none") |>
mutate(Parameter1 = paste0(str_replace(Parameter1, "_", " ("), ")"),
Parameter2 = paste0(str_replace(Parameter2, "_", " ("), ")"))
p <- summary(r) |>
plot() +
theme_minimal()
list(r = r, plot = p)
}
r <- get_correlation(var = "YONI_")
r$plot
p_conf_yoni_total /
p_conf_yoni_cognitive /
p_conf_yoni_affective /
p_conf_yoni_physical +
patchwork::plot_annotation(title = "Theory of Mind", theme = theme(plot.title = element_text(hjust = 0.5)))
p_rt_yoni_total /
p_rt_yoni_cognitive /
p_rt_yoni_affective /
p_rt_yoni_physical +
patchwork::plot_annotation(title = "Theory of Mind", theme = theme(plot.title = element_text(hjust = 0.5)))
model <- glmmTMB(Confidence ~ Answer / (Condition * BES_Total) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_bes_total <- plot_effect(model, var = "BES_Total", outcome = "Confidence")
# p_conf_bes_total
model <- glmmTMB(RT ~ Answer / (Condition * BES_Total) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_bes_total <- plot_effect(model, var = "BES_Total", outcome = "RT")
# p_rt_bes_total
model <- glmmTMB(Confidence ~ Answer / (Condition * BES_Cognitive) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_bes_cognitive <- plot_effect(model, var = "BES_Cognitive", outcome = "Confidence")
# p_conf_bes_cognitive
model <- glmmTMB(RT ~ Answer / (Condition * BES_Cognitive) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_bes_cognitive <- plot_effect(model, var = "BES_Cognitive", outcome = "RT")
# p_rt_bes_cognitive
model <- glmmTMB(Confidence ~ Answer / (Condition * BES_Affective) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_bes_affective <- plot_effect(model, var = "BES_Affective", outcome = "Confidence")
# p_conf_bes_affective
model <- glmmTMB(RT ~ Answer / (Condition * BES_Affective) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_bes_affective <- plot_effect(model, var = "BES_Affective", outcome = "RT")
# p_rt_bes_affective
r <- get_correlation(var = "BES_")
r$plot
p_conf_bes_total /
p_conf_bes_cognitive /
p_conf_bes_affective +
patchwork::plot_annotation(title = "Empathy", theme = theme(plot.title = element_text(hjust = 0.5)))
p_rt_bes_total /
p_rt_bes_cognitive /
p_rt_bes_affective +
patchwork::plot_annotation(title = "Empathy", theme = theme(plot.title = element_text(hjust = 0.5)))
model <- glmmTMB(Confidence ~ Answer / (Condition * HCT_Accuracy) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_hct_accuracy <- plot_effect(model, var = "HCT_Accuracy", outcome = "Confidence")
model <- glmmTMB(RT ~ Answer / (Condition * HCT_Accuracy) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_hct_accuracy <- plot_effect(model, var = "HCT_Accuracy", outcome = "RT")
model <- glmmTMB(Confidence ~ Answer / (Condition * HCT_Confidence) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_hct_confidence <- plot_effect(model, var = "HCT_Confidence", outcome = "Confidence")
model <- glmmTMB(RT ~ Answer / (Condition * HCT_Confidence) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_hct_confidence <- plot_effect(model, var = "HCT_Confidence", outcome = "RT")
model <- glmmTMB(Confidence ~ Answer / (Condition * HCT_Awareness) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_hct_awareness <- plot_effect(model, var = "HCT_Awareness", outcome = "Confidence")
model <- glmmTMB(RT ~ Answer / (Condition * HCT_Awareness) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_hct_awareness <- plot_effect(model, var = "HCT_Awareness", outcome = "RT")
r <- get_correlation(var = "HCT_")
r$plot
# plot(correlation::cor_test(dfsub, "HCT_Accuracy", "LIE_Ability"))
p_conf_hct_accuracy /
p_conf_hct_confidence /
p_conf_hct_awareness +
patchwork::plot_annotation(title = "Interoception", theme = theme(plot.title = element_text(hjust = 0.5)))
p_rt_hct_accuracy /
p_rt_hct_confidence /
p_rt_hct_awareness +
patchwork::plot_annotation(title = "Interoception", theme = theme(plot.title = element_text(hjust = 0.5)))
model <- glmmTMB(Confidence ~ Answer / (Condition * MAIA_Total) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_maia_total <- plot_effect(model, var = "MAIA_Total", outcome = "Confidence")
model <- glmmTMB(RT ~ Answer / (Condition * MAIA_Total) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_maia_total <- plot_effect(model, var = "MAIA_Total", outcome = "RT")
model <- glmmTMB(Confidence ~ Answer / (Condition * MAIA_Noticing) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_maia_noticing <- plot_effect(model, var = "MAIA_Noticing", outcome = "Confidence")
model <- glmmTMB(RT ~ Answer / (Condition * MAIA_Noticing) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_maia_noticing <- plot_effect(model, var = "MAIA_Noticing", outcome = "RT")
model <- glmmTMB(Confidence ~ Answer / (Condition * MAIA_NotDistracting) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_maia_notdistracting <- plot_effect(model, var = "MAIA_NotDistracting", outcome = "Confidence")
model <- glmmTMB(RT ~ Answer / (Condition * MAIA_NotDistracting) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_maia_notdistracting <- plot_effect(model, var = "MAIA_NotDistracting", outcome = "RT")
model <- glmmTMB(Confidence ~ Answer / (Condition * MAIA_BodyListening) + (1|Participant) + (1|Item),
data = df, family = beta_family())
results <- get_parameters(model)
results$params
results$marginal_effects
p_conf_maia_bodylistening <- plot_effect(model, var = "MAIA_BodyListening", outcome = "Confidence")
model <- glmmTMB(RT ~ Answer / (Condition * MAIA_BodyListening) + (1|Participant) + (1|Item),
data = df)
results <- get_parameters(model)
results$params
results$marginal_effects
p_rt_maia_bodylistening <- plot_effect(model, var = "MAIA_BodyListening", outcome = "RT")
r <- get_correlation(var = "MAIA_")
r$plot +
theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1))
p_conf_maia_total /
p_conf_maia_noticing /
p_conf_maia_notdistracting /
p_conf_maia_bodylistening +
patchwork::plot_annotation(title = "Interoception (MAIA)", theme = theme(plot.title = element_text(hjust = 0.5)))
p_rt_maia_total /
p_rt_maia_noticing /
p_rt_maia_notdistracting /
p_rt_maia_bodylistening +
patchwork::plot_annotation(title = "Interoception (MAIA)", theme = theme(plot.title = element_text(hjust = 0.5)))report::cite_packages(sessionInfo())